Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Multiple model-based reinforcement learning.

Kenji Doya1, Kazuyuki Samejima, Ken-ichi Katagiri

  • 1Human Information Science Laboratories, ATR International, Seika, Soraku, Kyoto 619-0288, Japan. doya@atr.co.jp

Neural Computation
|May 22, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Consensus Paper: Models of Cerebellar Functions.

Cerebellum (London, England)·2026
Same author

Extraction of robust functional connectivity patterns across psychiatric disorders using principal component analysis-based feature selection.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

A computational model of canonical cortical microcircuits for dynamic Bayesian inference and control as inference.

Neuroscience research·2025
Same author

Generalizable stratification based on thalamo-somatomotor functional connectivity predicts responses to antidepressants in patients with depression.

Molecular psychiatry·2025
Same author

Computational mechanisms of neuroimaging biomarkers uncovered by multicenter resting-state fMRI connectivity variation profile.

Molecular psychiatry·2025
Same author

Enhancement of the left frontoparietal network through real-time functional magnetic resonance imaging functional connectivity-informed neurofeedback and its impact on working memory in schizophrenia: A pilot study.

Psychiatry and clinical neurosciences·2025
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

We introduce multiple model-based reinforcement learning (MMRL), a modular approach for complex control tasks. MMRL decomposes problems, enabling adaptive learning in changing environments for improved performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Control Theory

Background:

  • Traditional reinforcement learning struggles with nonlinear, nonstationary control tasks.
  • Task complexity often arises from unpredictable environmental dynamics.

Purpose of the Study:

  • To propose a novel modular reinforcement learning architecture, Multiple Model-based Reinforcement Learning (MMRL).
  • To address challenges in nonlinear and nonstationary control by decomposing complex tasks.

Main Methods:

  • Decomposing tasks into domains based on environmental dynamics predictability.
  • Utilizing multiple modules, each with a state prediction model and RL controller.
  • Employing a 'responsibility signal' from prediction errors to weight module outputs and gate learning.

Related Experiment Videos

Main Results:

  • Demonstrated MMRL's effectiveness in a discrete nonstationary hunting task.
  • Validated MMRL's performance in a continuous nonlinear, nonstationary pendulum control task with variable parameters.

Conclusions:

  • MMRL offers a robust framework for tackling complex, dynamic control problems.
  • The modular approach enhances adaptability and learning efficiency in changing environments.